This invention provides a signal processing apparatus for improving the speech determination accuracy in an input sound. The signal processing apparatus includes a transformer that transforms an input signal into an amplitude component signal in a frequency domain, a calculator that calculates a norm of a change in the amplitude component signal in a frequency direction, an accumulator that accumulates the norm of the change in the amplitude component signal in the frequency direction calculated by the calculator, and an analyzer that analyzes speech in the input signal in accordance with an accumulated value of the norm of the change in the amplitude component signal in the frequency direction calculated by the accumulator.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A signal processing apparatus comprising: a processor; and a memory configured to store instructions executable by the processor, wherein the processor is configured to: transform input signal samples into frames of amplitude components representing different frequencies in a frequency domain; smooth the amplitude components along time to obtain time-smoothed amplitude components, smooth the time-smoothed amplitude components along frequency to obtain frequency-smoothed amplitude components; calculate differences of the frequency-smoothed amplitude components along the frequency; accumulate the differences to obtain an accumulated value; and analyze the input signal samples to detect a male voice in accordance with the accumulated value.
2. The signal processing apparatus according to claim 1 , wherein said processor is further configured to detect a female voice or a child voice in the input signal samples in accordance with the accumulated value.
3. The signal processing apparatus according to claim 1 , wherein said processor is further configured to detect a voice of a specific person by comparing the accumulated value with an accumulated value of the specific person which is stored in advance.
4. A signal processing method implemented using a signal processing apparatus, the method comprising: transforming, by the signal processing apparatus, input signal samples into frames of amplitude components representing different frequencies in a frequency domain; smoothing, by the signal processing apparatus, the amplitude components along time to obtain time-smoothed amplitude components, smoothing, by the signal processing apparatus, the time-smoothed amplitude components along frequency to obtain frequency-smoothed amplitude components; calculating, by the signal processing apparatus, differences of the frequency-smoothed amplitude components along the frequency; accumulating, by the signal processing apparatus, the differences to obtain an accumulated value; and analyzing, by the signal processing apparatus, the input signal samples to detect a male voice in accordance with the accumulated value.
5. A non-transitory computer readable medium storing a signal processing program for causing a signal processing apparatus to execute a method comprising: transforming input signal samples into frames of amplitude components representing different frequencies in a frequency domain; smoothing the amplitude components along time to obtain time-smoothed amplitude components, smoothing the time-smoothed amplitude components along frequency to obtain frequency-smoothed amplitude components; calculating differences of the frequency-smoothed amplitude components along the frequency; accumulating the differences to obtain an accumulated value; and analyzing the input signal samples to detect a male voice in accordance with the accumulated value.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 27, 2014
October 1, 2019
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.